Polly

Multi-agent coding orchestrator. Polly breaks your task into sub-tasks and delegates each one to a different AI agent, with cross-vendor code review built in.

omni polly
omni          # also launches Polly when a Claude credential is configured

How it works

Polly is a supervisor that never writes code itself. It decomposes your goal into sub-tasks and delegates each one to a sub-agent running on its own harness and git worktree. One agent implements, a different agent reviews. Each implementer opens its own PR. Polly never merges. The human decides.

Sub-agentHarnessRole
claude_codeclaude-nativeClaude Code
codexcodex-nativeCodex
opencodeopencode-nativeOpenCode
cursorcursor-nativeCursor
hermeshermes-nativeHermes Agent (Nous Research)
pipiPi (headless, any gateway model)

claude_code, codex, opencode, cursor, and hermes are the primary implementers, each running as a real CLI coding harness in its own terminal you can open in the UI's Subagents panel to watch or take over. pi runs headless as the review/explore specialist. Six distinct vendors means any implementer's diff can be reviewed by a different one — the cross-vendor check is the point.

Tool approvals in headless workers

Polly's native workers launch in a headless pane where no human is watching to answer a tool-approval prompt, so an Edit/Write/Bash that would prompt stalls the worker. Each worker's bundle therefore declares a full-bypass stance so it can edit and run unattended:

WorkerHarnessBypass configEffect
claude_codeclaude-nativepermission_mode: autopassed through as --permission-mode auto
codexcodex-nativeyolo: true--dangerously-bypass-approvals-and-sandbox
cursorcursor-nativeyolo: true--yolo (cursor-agent's don't-ask / full bypass)

Set executor.config.yolo: false on a worker to keep it prompting — useful for a read-only or must-approve sub-agent (its gated calls then surface as approval cards). For the Cursor worker, executor.config.permission_mode: auto (or exec_mode: auto / auto-review) selects Smart Auto (--auto-review) instead of full --yolo, matching Claude's permission_mode: auto ergonomics.

Bypass only skips the interactive per-tool prompt — Omnigent's blast_radius policy still DENYs the catastrophic set.

Skills

When to use

Source on GitHub